Recommending lifestyle articles is of immediate interest to theffecommerce industry and is beginning to attract research attention. Offen followed strategies, such as recommending popular items are inadequate for this vertical because of two reasons. Firstly, users have their own personal preference over items, referred to as personal styles, which lead to the long-tail phenomenon. Secondly, each user displays multiple personas, each persona has a preference over items which could be dictated by a particular occasion, e.g. dressing for a party would be different from dressing to go to o?ce. Recommendation in this vertical is crucially dependent on discovering styles for each of the multiple personas. There is no literature which addresses this problem. We posit a generative model which describes each user by a Simplex Over PERsona, SOPER, where a persona is described as the individuals preferences over prevailing styles modelled as topics over items. The choice of simplex and the long-tail nature necessitates the use of stick-breaking process. The main technical contribution is an efficient collapsed Gibbs sampling based algorithm for solving the attendant inference problem. Trained on large-scale interaction logs spanning more than halfa-million sessions collected from an e-commerce portal, SOPER outperforms previous baselines such as [9] by a large margin of 35% in identifying persona. Consequently it outperforms several competitive baselines comprehensively on the task of recommending from a catalogue of roughly 150 thousand lifestyle articles, by improving the recommendation quality as measured by AUC by a staggering 12:23%, in addition to aiding the interpretability of uncovered personal and fashionable styles thus advancing our precise understanding of the underlying phenomena. © 2017 ACM.